This manuscript analyzes the optical properties of dystrophic mice legs, which have been obtained by Spatial Frequency Domain Imaging (SFDI). We used a custom-built SFDI system with spectrometric capabilities so that wavelength-resolved absorption (μa) and scattering (μ′s) coefficients can be calculated. Samples were measured sequentially at ten different frequencies to find their frequency-dependent diffuse reflectance. Additionally, the Monte Carlo method has been applied to generate a Look-Up Table (LUT) to speed up the estimation of the optical parameters, with the GPU-accelerated version of Monte Carlo for Multi-Layered tissues (MCML), CUDAMCML. We found that the diffuse reflectance (Rd) has a different behavior in terms of the wavelength (λ), which gave rise to different values of µa and μ′s in terms of λ. Given that the μa is related to the chemical composition, the differences in wavelength could be used to quantify the presence of chemical components in the samples and, the μ′s, which relates to the internal structure, can be utilized to identify dystrophy centers inside the mice leg.
Profilometry is the technique that estimates the surface height and tomography of a sample. This technique is crucial to correct the intensity variations and angle changes when optical properties of a sample are estimated and its calculation depends on the surface profile. Two systems have been evaluated in this work: an Optical Coherence Tomography (OCT) system and a Spatial-Frecuency Domain Imaging (Hyperspectral-SFDI) system made up of a rotating mirror hyperspectral camera and a Red-Green-Blue (RGB) projector. The estimation of the height map with the OCT system based on the high contrasted backscattering of the air-sample interface whereas, while with the HSI-SFDI system the Phase Shifting Profilometry (PSP) technique has been implemented employing different frequencies. This work compares both approaches and evaluates the differences between them.
In this work, intensity and polarization OCT were applied, simultaneously, to alpha-sarcoglycan deficit mice models, and a new visualization technique was implemented, based on encoding the attenuation and birefringence values in the HSV color space. Our samples consisted of 14 ex-vivo mice quadriceps at different disease stages (one, three, and six-month-old mice) and four healthy ones for reference. The healthy muscles present a different birefringence distribution to the dystrophic ones, while attenuation values for both kinds of samples lay in the same range. Nevertheless, the attenuation provides an increase in contrast and textural features that are not visible by only using birefringence, while the latter, encoded in the H coordinate, helps to easily identify damage inside the samples by color.
The combination of molecular (hyperspectral imaging) and morphological (optical coherent tomography imaging) optical technologies helps in the assessment of biological tissue both in pathological diagnosis and in the follow-up treatments. The co-registration of both imaging features allows quantifying the presence of chromophores and the subsurface structure of tissue. This work proposes the fusion of two optical imaging technologies for the characterization of different types of tissues where the attenuation coefficient calculated from OCT imaging serves to track the presence of anomalies in the distribution of chromophores over the sample and therefore to diagnose pathological conditions. The performance of two customized hyperspectral imaging systems working in two complementary spectral ranges (VisNIR from 400 to 1000 nm, and SWIR 1000 to 1700 nm) and one commercial OCT system working at 1325 nm reveals the presence of fibrosis, collagen alterations and lipid content in cardiovascular tissues such as aortic walls (to assess on aneurysmal conditions) or tendinous chords (to diagnose the integrity of the valvular system) or in muscular diseases prone to fibrotic changes and inflammation.
With an adequate tissue dataset, supervised classification of tissue optical properties can be achieved in SFDI images of breast cancer lumpectomies with deep convolutional networks. Nevertheless, the use of a black-box classifier in current ex vivo setups provides output diagnostic images that are inevitably bound to show misclassified areas due to inter- and intra-patient variability that could potentially be misinterpreted in a real clinical setting. This work proposes the use of a novel architecture, the self-introspective classifier, where part of the model is dedicated to estimating its own expected classification error. The model can be used to generate metrics of self-confidence for a given classification problem, which can then be employed to show how much the network is familiar with the new incoming data. A heterogenous ensemble of four deep convolutional models with self-confidence, each sensitive to a different spatial scale of features, is tested on a cohort of 70 specimens, achieving a global leave-one-out cross-validation accuracy of up to 81%, while being able to explain where in the output classification image the system is most confident.
Margin assessment in gross pathology is becoming feasible as various explanatory deep learning-powered methods are able to obtain models for macroscopic textural information, tissue microstructure, and local surface optical properties. Unfortunately, each different method seems to lack enough diagnostic power to perform an adequate classification on its own. This work proposes using several separately trained deep convolutional networks, and averaging their responses, in order to achieve a better margin assessment. Qualitative leave-one-out cross-validation results are discussed for a cohort of 70 samples.
This work proposes separating data analysis from hyperspectral enhancement or editing, providing a robust, context-independent, fully-tunable framework for biomarker-based contrast in wide-field imaging with a series of reliable properties that could enable its use in guided surgery. Some applications of this method powered by deep learning diagnostics will be discussed and shown.
KEYWORDS: Raman spectroscopy, Digital filtering, Signal to noise ratio, Sensors, Spatial resolution, Denoising, Temperature sensors, Electronic filtering, Signal attenuation
In this work, a deep convolutional adaptive filter is proposed to enhance the performance of a Raman based distributed temperature sensor system by the application of domain randomization methods for its training. The improvement of the signal-to-noise ratio in the Raman backscattered signals in the training process and translation to a real scenario is demonstrated. The ability of the proposed technique to reduce signal noise effectively is proved independently of the sensor configuration and without degradation of temperature accuracy or spatial resolution of these systems. Moreover, using single trace to noise reduction in the ROTDR signals accelerates the system response avoiding the employment of many averages in a unique measurement
Extracting pathology information embedded within surface optical properties in Spatial Frequency Domain Imaging (SFDI) datasets is still a rather cumbersome nonlinear translation problem, mainly constrained by intrasample and interpatient variability, as well as dataset size. The β-variational autoencoder (β-VAE) is a rather novel dimensionality reduction technique where a tractable set of latent low-dimensional embeddings can be obtained from a given dataset. These embeddings can then be sampled to synthesize new data, providing further insight into pathology variability as well as differentiability in terms of optical properties. Its applications for data classification and breast margin delineation are also discussed.
Skin lesion segmentation is a complex step for dermoscopy pathological diagnosis. Kernel density estimation is proposed
as a segmentation technique based on the statistic distribution of color intensities in the lesion and non-lesion regions.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.